pytrilogy 0.0.2.37__tar.gz → 0.0.2.39__tar.gz

{pytrilogy-0.0.2.37/pytrilogy.egg-info → pytrilogy-0.0.2.39}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pytrilogy
-Version: 0.0.2.37
+Version: 0.0.2.39
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 

{pytrilogy-0.0.2.37 → pytrilogy-0.0.2.39/pytrilogy.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pytrilogy
-Version: 0.0.2.37
+Version: 0.0.2.39
 Summary: Declarative, typed query language that compiles to SQL.
 Home-page: 
 Author: 

{pytrilogy-0.0.2.37 → pytrilogy-0.0.2.39}/trilogy/__init__.py

@@ -4,6 +4,6 @@ from trilogy.executor import Executor
 from trilogy.parser import parse
 from trilogy.constants import CONFIG
 
-__version__ = "0.0.2.37"
+__version__ = "0.0.2.39"
 
 __all__ = ["parse", "Executor", "Dialects", "Environment", "CONFIG"]

{pytrilogy-0.0.2.37 → pytrilogy-0.0.2.39}/trilogy/core/models.py

@@ -2085,14 +2085,16 @@ class DatasourceMetadata(BaseModel):
 
 
 class MergeStatementV2(HasUUID, Namespaced, BaseModel):
-    source: Concept
-    target: Concept
+    sources: list[Concept]
+    targets: dict[str, Concept]
+    source_wildcard: str | None = None
+    target_wildcard: str | None = None
     modifiers: List[Modifier] = Field(default_factory=list)
 
     def with_namespace(self, namespace: str) -> "MergeStatementV2":
         new = MergeStatementV2(
-            source=self.source.with_namespace(namespace),
-            target=self.target.with_namespace(namespace),
+            sources=[x.with_namespace(namespace) for x in self.sources],
+            targets={k: v.with_namespace(namespace) for k, v in self.targets.items()},
             modifiers=self.modifiers,
         )
         return new
@@ -3383,7 +3385,7 @@ class Environment(BaseModel):
 
     def __init__(self, **data):
         super().__init__(**data)
-        self.concepts["_env_working_path"] = Concept(
+        concept = Concept(
             name="_env_working_path",
             namespace=self.namespace,
             lineage=Function(
@@ -3395,6 +3397,7 @@ class Environment(BaseModel):
             datatype=DataType.STRING,
             purpose=Purpose.CONSTANT,
         )
+        self.add_concept(concept)
 
     @classmethod
     def from_file(cls, path: str | Path) -> "Environment":

{pytrilogy-0.0.2.37 → pytrilogy-0.0.2.39}/trilogy/executor.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Any, Generator
+from typing import List, Optional, Any, Generator, Protocol
 from functools import singledispatchmethod
 from sqlalchemy import text
 from sqlalchemy.engine import Engine, CursorResult
@@ -36,6 +36,15 @@ from pathlib import Path
 from dataclasses import dataclass
 
 
+class ResultProtocol(Protocol):
+    values: List[Any]
+    columns: List[str]
+
+    def fetchall(self) -> List[Any]: ...
+
+    def keys(self) -> List[str]: ...
+
+
 @dataclass
 class MockResult:
     values: list[Any]
@@ -201,15 +210,16 @@ class Executor(object):
 
     @execute_query.register
     def _(self, query: MergeStatementV2) -> CursorResult:
+        for concept in query.sources:
+            self.environment.merge_concept(
+                concept, query.targets[concept.address], modifiers=query.modifiers
+            )
 
-        self.environment.merge_concept(
-            query.source, query.target, modifiers=query.modifiers
-        )
         return MockResult(
             [
                 {
-                    "source": query.source.address,
-                    "target": query.target.address,
+                    "sources": ",".join([x.address for x in query.sources]),
+                    "targets": ",".join([x.address for _, x in query.targets.items()]),
                 }
             ],
             ["source", "target"],
@@ -309,7 +319,20 @@ class Executor(object):
             output.append(compiled_sql)
         return output
 
-    def parse_file(self, file: str | Path, persist: bool = False) -> Generator[
+    def parse_file(
+        self, file: str | Path, persist: bool = False
+    ) -> list[
+        ProcessedQuery
+        | ProcessedQueryPersist
+        | ProcessedShowStatement
+        | ProcessedRawSQLStatement
+        | ProcessedCopyStatement,
+    ]:
+        return list(self.parse_file_generator(file, persist=persist))
+
+    def parse_file_generator(
+        self, file: str | Path, persist: bool = False
+    ) -> Generator[
         ProcessedQuery
         | ProcessedQueryPersist
         | ProcessedShowStatement

{pytrilogy-0.0.2.37 → pytrilogy-0.0.2.39}/trilogy/parsing/parse_engine.py

@@ -302,6 +302,9 @@ class ParseToObjects(Transformer):
     def IDENTIFIER(self, args) -> str:
         return args.value
 
+    def WILDCARD_IDENTIFIER(self, args) -> str:
+        return args.value
+
     def QUOTED_IDENTIFIER(self, args) -> str:
         return args.value[1:-1]
 
@@ -786,19 +789,47 @@ class ParseToObjects(Transformer):
         return [x for x in args]
 
     @v_args(meta=True)
-    def merge_statement_v2(self, meta: Meta, args) -> MergeStatementV2:
+    def merge_statement(self, meta: Meta, args) -> MergeStatementV2:
         modifiers = []
-        concepts = []
+        cargs: list[str] = []
+        source_wildcard = None
+        target_wildcard = None
         for arg in args:
             if isinstance(arg, Modifier):
                 modifiers.append(arg)
             else:
-                concepts.append(self.environment.concepts[arg])
+                cargs.append(arg)
+        source, target = cargs
+        if source.endswith(".*"):
+            if not target.endswith(".*"):
+                raise ValueError("Invalid merge, source is wildcard, target is not")
+            source_wildcard = source[:-2]
+            target_wildcard = target[:-2]
+            sources = [
+                v
+                for k, v in self.environment.concepts.items()
+                if v.namespace == source_wildcard
+            ]
+            targets = {}
+            for x in sources:
+                target = target_wildcard + "." + x.name
+                if target in self.environment.concepts:
+                    targets[x.address] = self.environment.concepts[target]
+            sources = [x for x in sources if x.address in targets]
+        else:
+            sources = [self.environment.concepts[source]]
+            targets = {sources[0].address: self.environment.concepts[target]}
         new = MergeStatementV2(
-            source=concepts[0], target=concepts[1], modifiers=modifiers
+            sources=sources,
+            targets=targets,
+            modifiers=modifiers,
+            source_wildcard=source_wildcard,
+            target_wildcard=target_wildcard,
         )
-
-        self.environment.merge_concept(new.source, new.target, modifiers)
+        for source_c in new.sources:
+            self.environment.merge_concept(
+                source_c, targets[source_c.address], modifiers
+            )
 
         return new
 
@@ -1745,7 +1776,7 @@ class ParseToObjects(Transformer):
             arguments=args,
             output_datatype=output_datatype,
             output_purpose=function_args_to_output_purpose(args),
-            # valid_inputs={DataType.DATE, DataType.TIMESTAMP, DataType.DATETIME},
+            valid_inputs={DataType.INTEGER, DataType.FLOAT, DataType.NUMBER},
             arg_count=2,
         )
 
@@ -1758,7 +1789,7 @@ class ParseToObjects(Transformer):
             arguments=args,
             output_datatype=output_datatype,
             output_purpose=function_args_to_output_purpose(args),
-            # valid_inputs={DataType.DATE, DataType.TIMESTAMP, DataType.DATETIME},
+            valid_inputs={DataType.INTEGER, DataType.FLOAT, DataType.NUMBER},
             arg_count=2,
         )
 
@@ -1771,20 +1802,21 @@ class ParseToObjects(Transformer):
             arguments=args,
             output_datatype=output_datatype,
             output_purpose=function_args_to_output_purpose(args),
-            # valid_inputs={DataType.DATE, DataType.TIMESTAMP, DataType.DATETIME},
+            valid_inputs={DataType.INTEGER, DataType.FLOAT, DataType.NUMBER},
             arg_count=2,
         )
 
     @v_args(meta=True)
     def fdiv(self, meta: Meta, args):
         args = process_function_args(args, meta=meta, environment=self.environment)
-        output_datatype = merge_datatypes([arg_to_datatype(x) for x in args])
+        # 2024-11-18 - this is a bit of a hack, but division always returns a float
+        # output_datatype = merge_datatypes([arg_to_datatype(x) for x in args])
         return Function(
             operator=FunctionType.DIVIDE,
             arguments=args,
-            output_datatype=output_datatype,
+            output_datatype=DataType.FLOAT,  # division always returns a float
             output_purpose=function_args_to_output_purpose(args),
-            # valid_inputs={DataType.DATE, DataType.TIMESTAMP, DataType.DATETIME},
+            valid_inputs={DataType.INTEGER, DataType.FLOAT, DataType.NUMBER},
             arg_count=2,
         )
 

{pytrilogy-0.0.2.37 → pytrilogy-0.0.2.39}/trilogy/parsing/render.py

@@ -432,7 +432,9 @@ class Renderer:
 
     @to_string.register
     def _(self, arg: MergeStatementV2):
-        return f"MERGE {self.to_string(arg.source)} into {''.join([self.to_string(modifier) for modifier in arg.modifiers])}{self.to_string(arg.target)};"
+        if len(arg.sources) == 1:
+            return f"MERGE {self.to_string(arg.sources[0])} into {''.join([self.to_string(modifier) for modifier in arg.modifiers])}{self.to_string(arg.targets[arg.sources[0].address])};"
+        return f"MERGE {arg.source_wildcard}.* into {''.join([self.to_string(modifier) for modifier in arg.modifiers])}{arg.target_wildcard}.*;"
 
     @to_string.register
     def _(self, arg: Modifier):

{pytrilogy-0.0.2.37 → pytrilogy-0.0.2.39}/trilogy/parsing/trilogy.lark

@@ -9,7 +9,7 @@
     | rowset_derivation_statement
     | import_statement
     | copy_statement
-    | merge_statement_v2
+    | merge_statement
     | rawsql_statement
     
     _TERMINATOR:  ";"i /\s*/
@@ -74,8 +74,7 @@
 
     align_clause: align_item ("AND"i align_item)*  "AND"i?
 
-    // merge_v2
-    merge_statement_v2: "merge"i  IDENTIFIER "into"i SHORTHAND_MODIFIER? IDENTIFIER 
+    merge_statement: "merge"i  WILDCARD_IDENTIFIER "into"i SHORTHAND_MODIFIER? WILDCARD_IDENTIFIER
 
     // raw sql statement
     rawsql_statement: "raw_sql"i "(" MULTILINE_STRING ")"
@@ -292,6 +291,7 @@
     // base language constructs
     concept_lit: IDENTIFIER
     IDENTIFIER: /[a-zA-Z\_][a-zA-Z0-9\_\-\.]*/
+    WILDCARD_IDENTIFIER: /[a-zA-Z\_][a-zA-Z0-9\_\-\.\*]*/
     QUOTED_IDENTIFIER:  /`[a-zA-Z\_][a-zA-Z0-9\_\.\-\*\:\s]*`/
     QUOTED_ADDRESS:  /`[a-zA-Z\_][a-zA-Z0-9\_\.\-\*\:]*`/
     ADDRESS: IDENTIFIER